Utilizing character and word embeddings for text normalization with sequence-to-sequence models

12Citations
Citations of this article
94Readers
Mendeley users who have this article in their library.

Abstract

Text normalization is an important enabling technology for several NLP tasks. Recently, neural-network-based approaches have outperformed well-established models in this task. However, in languages other than English, there has been little exploration in this direction. Both the scarcity of annotated data and the complexity of the language increase the difficulty of the problem. To address these challenges, we use a sequence-to-sequence model with character-based attention, which in addition to its self-learned character embeddings, uses word embeddings pre-trained with an approach that also models subword information. This provides the neural model with access to more linguistic information especially suitable for text normalization, without large parallel corpora. We show that providing the model with word-level features bridges the gap for the neural network approach to achieve a state-of-the-art F1 score on a standard Arabic language correction shared task dataset.

Cite

CITATION STYLE

APA

Watson, D., Zalmout, N., & Habash, N. (2018). Utilizing character and word embeddings for text normalization with sequence-to-sequence models. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 (pp. 837–843). Association for Computational Linguistics. https://doi.org/10.18653/v1/d18-1097

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free